# Design Principles of Robust Multi-Armed Bandit Framework in Video Recommendations

arXiv: https://arxiv.org/abs/2310.01419 · HTML: https://mlsanity.com/paper/2310.01419/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 19 references that are in the map.
- First posted on arXiv 24 Sep 2023.

## Builds on (most cited first, 8 of 8)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Joint Deep Modeling of Users and Items Using Reviews for Recommendation](https://mlsanity.com/paper/1701.04783/) (2017)
- [The Unfairness of Popularity Bias in Recommendation](https://mlsanity.com/paper/1907.13286/) (2019)
- [A Survey on Contextual Multi-armed Bandits](https://mlsanity.com/paper/1508.03326/) (2015)
- [Continual Learning for Instruction Following from Realtime Feedback](https://mlsanity.com/paper/2212.09710/) (2022)
- [Fairness Implications of Encoding Protected Categorical Attributes](https://mlsanity.com/paper/2201.11358/) (2022)
- [Random Forests, Decision Trees, and Categorical Predictors: The "Absent Levels" Problem](https://mlsanity.com/paper/1706.03492/) (2017)
- [Data Augmentation Strategies for Improving Sequential Recommender Systems](https://mlsanity.com/paper/2203.14037/) (2022)

## Abstract (arXiv)

Current multi-armed bandit approaches in recommender systems (RS) have focused more on devising effective exploration techniques, while not adequately addressing common exploitation challenges related to distributional changes and item cannibalization. Little work exists to guide the design of robust bandit frameworks that can address these frequent challenges in RS. In this paper, we propose a new design principles to (i) make bandit models robust to time-variant metadata signals, (ii) less prone to item cannibalization, and (iii) prevent their weights fluctuating due to data sparsity. Through a series of experiments, we systematically examine the influence of several important bandit design choices. We demonstrate the advantage of our proposed design principles at making bandit models robust to dynamic behavioral changes through in-depth analyses. Noticeably, we show improved relative gain compared to a baseline bandit model not incorporating our design choices of up to 11.88% and 44.85%, respectively in ROC-AUC and PR-AUC. Case studies about fairness in recommending specific popular and unpopular titles are presented, to demonstrate the robustness of our proposed design at addressing popularity biases.